# Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement

arXiv: https://arxiv.org/abs/2511.11702 · HTML: https://mlsanity.com/paper/2511.11702/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 12 Nov 2025.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [OpenMask3D: Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2306.13631/) (2023)
- [3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2003.13867/) (2020)
- [Superpoint Transformer for 3D Scene Instance Segmentation](https://mlsanity.com/paper/2211.15766/) (2022)
- [3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection](https://mlsanity.com/paper/2204.06272/) (2022)
- [OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation](https://mlsanity.com/paper/2309.00616/) (2023)
- [Grounding 3D Object Affordance from 2D Interactions in Images](https://mlsanity.com/paper/2303.10437/) (2023)
- [One-Shot Open Affordance Learning with Foundation Models](https://mlsanity.com/paper/2311.17776/) (2023)
- [3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation](https://mlsanity.com/paper/2308.16632/) (2023)
- [3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds](https://mlsanity.com/paper/2502.20041/) (2025)
- [GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding](https://mlsanity.com/paper/2411.19626/) (2024)
- [EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views](https://mlsanity.com/paper/2405.13659/) (2024)
- [Open-Vocabulary Affordance Detection using Knowledge Distillation and Text-Point Correlation](https://mlsanity.com/paper/2309.10932/) (2023)
- [GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency](https://mlsanity.com/paper/2412.09511/) (2024)
- [Functionality understanding and segmentation in 3D scenes](https://mlsanity.com/paper/2411.16310/) (2024)
- [Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors](https://mlsanity.com/paper/2505.24103/) (2025)

## Built on by (most cited first, 6 of 6)

- [Action-guided generation of 3D functionality segmentation data](https://mlsanity.com/paper/2511.23230/) (2025)
- [UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Affordance Segmentation](https://mlsanity.com/paper/2603.23478/) (2026)
- [VoxAfford: Multi-Scale Voxel-Token Fusion for Open-Vocabulary 3D Affordance Detection](https://mlsanity.com/paper/2605.01365/) (2026)
- [Grounding by Remembering: Cross-Scene and In-Scene Memory for 3D Functional Affordances](https://mlsanity.com/paper/2605.11616/) (2026)
- [EgoAfford: Task-Oriented Affordance Grounding via Egocentric Referring Segmentation](https://mlsanity.com/paper/2608.04533/) (2026)
- [ThinkAfford: Affordance-Centric Reasoning for Fine-Grained 3D Grounding in Cluttered Scenes](https://mlsanity.com/paper/2608.10981/) (2026)

## Abstract (arXiv)

Understanding 3D scene-level affordances from natural language instructions is essential for enabling embodied agents to interact meaningfully in complex environments. However, this task remains challenging due to the need for semantic reasoning and spatial grounding. Existing methods mainly focus on object-level affordances or merely lift 2D predictions to 3D, neglecting rich geometric structure information in point clouds and incurring high computational costs. To address these limitations, we introduce Task-Aware 3D Scene-level Affordance segmentation (TASA), a novel geometry-optimized framework that jointly leverages 2D semantic cues and 3D geometric reasoning in a coarse-to-fine manner. To improve the affordance detection efficiency, TASA features a task-aware 2D affordance detection module to identify manipulable points from language and visual inputs, guiding the selection of task-relevant views. To fully exploit 3D geometric information, a 3D affordance refinement module is proposed to integrate 2D semantic priors with local 3D geometry, resulting in accurate and spatially coherent 3D affordance masks. Experiments on SceneFun3D demonstrate that TASA significantly outperforms the baselines in both accuracy and efficiency in scene-level affordance segmentation.